libtv-skill

Warn

Audited by Snyk on Mar 18, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.70). The skill calls the external agent-im API (e.g., GET /openapi/session/:sessionId via scripts/query_session.py against https://im.liblib.tv) and reads/returns message contents and result URLs from that third-party service (user/assistant messages), which the agent is expected to interpret and use to drive outputs, so untrusted remote content can influence subsequent actions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 18, 2026, 11:43 AM
Issues
1